Advertisement

Newton Filters: a New Class of Neuron-Like Discrete Filters and an Application to Image Processing

  • Alexis Quesada-Arencibia
  • Miguel Alemán-Flores
  • Roberto Moreno-DiazJr.
Conference paper

Abstract

The functions of dentritic trees of neurons have always attracted neuroscientists. Dendrites are extensions of the soma that allows the cell to increase the area where it receives information from. The number of dentritic ramifications is not constant, it depends on the neuron and varies from one to the other. Moreover, each dentritic tree can be subdivided in a complex form leading to a characteristic tree structure [1]. Two of their immediately-related properties regarding information processing (e.g. convergence and divergence of lines) have originated considerable research on completeness of computation and reliability of transmission [2]. In this paper a layered structure consisting in the interconnections of a set of simple functional units and inspired in the dentritic connections of real neurons, is suggested and in a parallel way we analyze the computing properties and characteristics together with a possible application in Image Processing. The interest of this structure lies in its similarity with the structure of the retinae receptive fields and even with dentritic trees of retinal neurons.

Keywords

Receptive Field Additive Layer Computational Unit Global Weight Computational Kernel 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    McLennan H. (1970) Synaptic Transmission. W. B. Sanders Company Philadelphia. USA.Google Scholar
  2. [2]
    Moreno-Diaz R., Moreno-Diaz jr R., Leibovic K. N., Systems optimization in retinal research, Lecture Notes in Computer Science, Vol. 585, pp. 539–546, (EUROCAST91), Munich, 1991.CrossRefGoogle Scholar
  3. [3]
    Moreno-Diaz jr R., Computation Paralela y Distribuida: relation estructura-funcion en retinas, Tesis Doctoral (PhD Dissertation). Las Palmas, 1993. ISBN: 84-8090-019-2.Google Scholar
  4. [4]
    Moreno-Diaz R., Rubio Royo E., A model for nonlinear processing in cat’s retina, Biological Cybernetics, Vol. 35, 1980.Google Scholar
  5. [5]
    Aleman-Flores M., Leibovic N., Moreno-Diaz R. jr. “A Computational Model for Visual Size, Location and Movement”. Lecture Notes in Computer Science, Vol. 1333, Springer, EUROCAST′97.Google Scholar

Copyright information

© Springer-Verlag Wien 1999

Authors and Affiliations

  • Alexis Quesada-Arencibia
    • 1
    • 3
  • Miguel Alemán-Flores
    • 2
    • 3
  • Roberto Moreno-DiazJr.
    • 1
    • 3
  1. 1.Instituto Universitario de Ciencias y Tecnologías CibernéticasULPGCLas PalmasSpain
  2. 2.Departamento de Informática y SistemasULPGCLas PalmasSpain
  3. 3.Edificio de Informática y MatemácasLas PalmasSpain

Personalised recommendations